def compute_bench_2(chunks):
results = defaultdict(lambda: [])
n_features = 50000
means = np.array([[1, 1], [-1, -1], [1, -1], [-1, 1], [0.5, 0.5],
[0.75, -0.5], [-1, 0.75], [1, 0]])
X = np.empty((0, 2))
for i in xrange(8):
X = np.r_[X, means[i] + 0.8 * np.random.randn(n_features, 2)]
max_it = len(chunks)
it = 0
for chunk in chunks:
it += 1
print '=============================='
print 'Iteration %03d of %03d' % (it, max_it)
print '=============================='
print ''
print 'Fast K-Means'
tstart = time()
mbkmeans = MiniBatchKMeans(init='k-means++', k=8, chunk_size=chunk)
mbkmeans.fit(X)
delta = time() - tstart
print "Speed: %0.3fs" % delta
print "Inertia: %0.3fs" % mbkmeans.inertia_
print ''
results['minibatchkmeans_speed'].append(delta)
results['minibatchkmeans_quality'].append(mbkmeans.inertia_)
return results
def compute_bench_2(chunks):
results = defaultdict(lambda: [])
n_features = 50000
means = np.array([[1, 1], [-1, -1], [1, -1], [-1, 1], [0.5, 0.5], [0.75, -0.5], [-1, 0.75], [1, 0]])
X = np.empty((0, 2))
for i in xrange(8):
X = np.r_[X, means[i] + 0.8 * np.random.randn(n_features, 2)]
max_it = len(chunks)
it = 0
for chunk in chunks:
it += 1
print "=============================="
print "Iteration %03d of %03d" % (it, max_it)
print "=============================="
print ""
print "Fast K-Means"
tstart = time()
mbkmeans = MiniBatchKMeans(init="k-means++", k=8, chunk_size=chunk)
mbkmeans.fit(X)
delta = time() - tstart
print "Speed: %0.3fs" % delta
print "Inertia: %0.3fs" % mbkmeans.inertia_
print ""
results["minibatchkmeans_speed"].append(delta)
results["minibatchkmeans_quality"].append(mbkmeans.inertia_)
return results
def compute_bench(samples_range, features_range):
it = 0
iterations = 200
results = defaultdict(lambda: [])
chunk = 100
max_it = len(samples_range) * len(features_range)
for n_samples in samples_range:
for n_features in features_range:
it += 1
print '=============================='
print 'Iteration %03d of %03d' %(it, max_it)
print '=============================='
print ''
data = nr.random_integers(-50, 50, (n_samples, n_features))
print 'K-Means'
tstart = time()
kmeans = KMeans(init='k-means++',
k=10).fit(data)
delta = time() - tstart
print "Speed: %0.3fs" % delta
print "Inertia: %0.5f" % kmeans.inertia_
print ''
results['kmeans_speed'].append(delta)
results['kmeans_quality'].append(kmeans.inertia_)
print 'Fast K-Means'
# let's prepare the data in small chunks
mbkmeans = MiniBatchKMeans(init='k-means++',
k=10,
chunk_size=chunk)
tstart = time()
mbkmeans.fit(data)
delta = time() - tstart
print "Speed: %0.3fs" % delta
print "Inertia: %f" % mbkmeans.inertia_
print ''
print ''
results['minibatchkmeans_speed'].append(delta)
results['minibatchkmeans_quality'].append(mbkmeans.inertia_)
return results
def compute_bench(samples_range, features_range):
it = 0
iterations = 200
results = defaultdict(lambda: [])
chunk = 100
max_it = len(samples_range) * len(features_range)
for n_samples in samples_range:
for n_features in features_range:
it += 1
print '=============================='
print 'Iteration %03d of %03d' % (it, max_it)
print '=============================='
print ''
data = nr.random_integers(-50, 50, (n_samples, n_features))
print 'K-Means'
tstart = time()
kmeans = KMeans(init='k-means++', k=10).fit(data)
delta = time() - tstart
print "Speed: %0.3fs" % delta
print "Inertia: %0.5f" % kmeans.inertia_
print ''
results['kmeans_speed'].append(delta)
results['kmeans_quality'].append(kmeans.inertia_)
print 'Fast K-Means'
# let's prepare the data in small chunks
mbkmeans = MiniBatchKMeans(init='k-means++',
k=10,
chunk_size=chunk)
tstart = time()
mbkmeans.fit(data)
delta = time() - tstart
print "Speed: %0.3fs" % delta
print "Inertia: %f" % mbkmeans.inertia_
print ''
print ''
results['minibatchkmeans_speed'].append(delta)
results['minibatchkmeans_quality'].append(mbkmeans.inertia_)
return results
